google-gemma-4-31b-it

developer_uid: rirv938

submission_id: google-gemma-4-31b-it_v21

model_name: google-gemma-4-31b-it_v21

model_group: google/gemma-4-31B-it

status: inactive

timestamp: 2026-04-08T01:43:42+00:00

num_battles: 3525

num_wins: 1681

celo_rating: 1297.94

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: google/gemma-4-31B-it

model_architecture: Gemma4ForConditionalGeneration

model_num_parameters: 28830461184.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 80

reward_model: default

display_name: google-gemma-4-31b-it_v21

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: google/gemma-4-31B-it

model_size: 29B

ranking_group: single

us_pacific_date: 2026-04-07

win_ratio: 0.4768794326241135

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 64, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['###', '<turn|>', '<|turn>', '</s>', '<|im_start|>', '<|redacted_im_end|>', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 80}

formatter: {'memory_template': '<|turn>system\nYou are "{bot_name}". Stay in character and respond only as "{bot_name}". You are allowed to be NSFW in the response if relevant to the conversation. Create an entertaining dialogue.<turn|>\n', 'prompt_template': '', 'bot_template': '<|turn>model\n{message}<turn|>\n', 'user_template': '<|turn>user\n{message}<turn|>\n', 'response_template': '<|turn>model\n', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name google-gemma-4-31b-it-v21-uploader
Waiting for job on google-gemma-4-31b-it-v21-uploader to finish
google-gemma-4-31b-it-v21-uploader: Using quantization_mode: none
google-gemma-4-31b-it-v21-uploader: Downloading snapshot of google/gemma-4-31B-it...
google-gemma-4-31b-it-v21-uploader: Downloaded in 33.393s
2026-04-08T00:04:10.704928+00:00 monitor updated for google-gemma-4-31b-it_v21
google-gemma-4-31b-it-v21-uploader: Processed model google/gemma-4-31B-it in 55.546s
google-gemma-4-31b-it-v21-uploader: creating bucket guanaco-vllm-models
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
google-gemma-4-31b-it-v21-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
google-gemma-4-31b-it-v21-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
google-gemma-4-31b-it-v21-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
google-gemma-4-31b-it-v21-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
google-gemma-4-31b-it-v21-uploader:   if re.search("-\.", bucket, re.UNICODE):
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
google-gemma-4-31b-it-v21-uploader:   if re.search("\.\.", bucket, re.UNICODE):
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
google-gemma-4-31b-it-v21-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
google-gemma-4-31b-it-v21-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
google-gemma-4-31b-it-v21-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
google-gemma-4-31b-it-v21-uploader: Bucket 's3://guanaco-vllm-models/' created
google-gemma-4-31b-it-v21-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/chat_template.jinja
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/processor_config.json s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/processor_config.json
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/README.md
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/generation_config.json
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/.gitattributes
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/config.json
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/tokenizer.json
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/model.safetensors.index.json
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/tokenizer_config.json
2026-04-08T00:05:10.906221+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:06:11.491218+00:00 monitor updated for google-gemma-4-31b-it_v21
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/model-00002-of-00002.safetensors s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/model-00002-of-00002.safetensors
2026-04-08T00:07:12.036605+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:08:12.294683+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:09:13.436444+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:10:14.488547+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:11:14.814307+00:00 monitor updated for google-gemma-4-31b-it_v21
google-gemma-4-31b-it-v21-uploader: cp /dev/shm/model_output/model-00001-of-00002.safetensors s3://guanaco-vllm-models/google-gemma-4-31b-it-v21/default/model-00001-of-00002.safetensors
Job google-gemma-4-31b-it-v21-uploader completed after 498.93s with status: succeeded
Stopping job with name google-gemma-4-31b-it-v21-uploader
Pipeline stage VLLMUploader completed in 500.90s
run pipeline stage %s
Running pipeline stage VLLMUploaderAMD
Pipeline stage vllm_upload_amd skipped, reason=not amd cluster
Pipeline stage VLLMUploaderAMD completed in 0.55s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.81s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service google-gemma-4-31b-it-v21
Waiting for inference service google-gemma-4-31b-it-v21 to be ready
2026-04-08T00:12:15.160858+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:13:16.080251+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:14:16.411110+00:00 monitor updated for google-gemma-4-31b-it_v21
2026-04-08T00:15:16.762336+00:00 monitor updated for google-gemma-4-31b-it_v21
Inference service google-gemma-4-31b-it-v21 ready after 264.1835820674896s
Pipeline stage VLLMDeployer completed in 266.66s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 12.098654985427856s
2026-04-08T00:16:17.092499+00:00 monitor updated for google-gemma-4-31b-it_v21
Received healthy response to inference request in 11.833079814910889s
Received healthy response to inference request in 11.78167986869812s
Received healthy response to inference request in 5.590334892272949s
Received healthy response to inference request in 4.34498143196106s
Received healthy response to inference request in 4.246066093444824s
Received healthy response to inference request in 4.251725435256958s
Received healthy response to inference request in 4.395503044128418s
Received healthy response to inference request in 5.149908781051636s
Received healthy response to inference request in 4.473663568496704s
2026-04-08T00:17:18.006820+00:00 monitor updated for google-gemma-4-31b-it_v21
Received healthy response to inference request in 4.751906633377075s
Received healthy response to inference request in 4.355188369750977s
Received healthy response to inference request in 4.403660535812378s
Received healthy response to inference request in 4.634203672409058s
Received healthy response to inference request in 4.489123106002808s
Received healthy response to inference request in 4.5881593227386475s
Received healthy response to inference request in 4.707441568374634s
Received healthy response to inference request in 12.408512115478516s
Received healthy response to inference request in 12.503428220748901s
2026-04-08T00:18:19.184263+00:00 monitor updated for google-gemma-4-31b-it_v21
Received healthy response to inference request in 4.382236957550049s
Received healthy response to inference request in 4.5222861766815186s
Received healthy response to inference request in 4.99561333656311s
Received healthy response to inference request in 4.484685182571411s
Received healthy response to inference request in 6.332512617111206s
Received healthy response to inference request in 4.313990354537964s
Received healthy response to inference request in 4.239044904708862s
Received healthy response to inference request in 4.349053859710693s
Received healthy response to inference request in 4.3809144496917725s
Received healthy response to inference request in 4.273956060409546s
Received healthy response to inference request in 4.460633277893066s
30 requests
0 failed requests
5th percentile: 4.248612797260284
10th percentile: 4.271732997894287
20th percentile: 4.348239374160767
30th percentile: 4.381840205192566
40th percentile: 4.437844181060791
50th percentile: 4.486904144287109
60th percentile: 4.606577062606812
70th percentile: 4.825018644332885
80th percentile: 5.7387704372406025
90th percentile: 11.859637331962587
95th percentile: 12.269076406955719
99th percentile: 12.47590255022049
mean time: 5.858071621259054
Pipeline stage StressChecker completed in 195.98s
Shutdown handler de-registered
2026-04-08T00:19:19.559482+00:00 monitor updated for google-gemma-4-31b-it_v21
google-gemma-4-31b-it_v21 status is now inactive due to admin request